© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57081
    Prev
    Next
    INDEX
    Explanations

    medical and surgical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÙħÙĪÙĨ
    -0.09
     Coff
    -0.09
    NSE
    -0.09
    头顶
    -0.08
    bsub
    -0.08
    bsp
    -0.08
    踮
    -0.08
    è·ĭ
    -0.08
    cimal
    -0.08
     Cron
    -0.08
    POSITIVE LOGITS
    æĭĨ
    0.12
    è£Ĥ
    0.11
    é»İæĺİ
    0.11
    åī²
    0.10
    ä¸ĢåĪĢ
    0.10
    åĩłåįĥ
    0.10
    åĪĢ
    0.10
    çł´è£Ĥ
    0.09
    为主线
    0.09
    è±ģ
    0.09
    Activations Density 0.098%

    No Known Activations